summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/Kconfig14
-rw-r--r--arch/x86/kernel/apic_32.c4
-rw-r--r--arch/x86/kernel/apic_64.c4
-rw-r--r--arch/x86/oprofile/Makefile2
-rw-r--r--arch/x86/oprofile/nmi_int.c27
-rw-r--r--arch/x86/oprofile/op_model_amd.c543
-rw-r--r--arch/x86/oprofile/op_model_athlon.c190
-rw-r--r--arch/x86/oprofile/op_model_p4.c175
-rw-r--r--arch/x86/oprofile/op_x86_model.h4
-rw-r--r--drivers/oprofile/buffer_sync.c209
-rw-r--r--drivers/oprofile/cpu_buffer.c74
-rw-r--r--drivers/oprofile/cpu_buffer.h2
-rw-r--r--include/linux/oprofile.h2
-rw-r--r--include/linux/pci_ids.h5
14 files changed, 901 insertions, 354 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index 364c6dadde0..0267babe5eb 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -13,6 +13,20 @@ config OPROFILE
If unsure, say N.
+config OPROFILE_IBS
+ bool "OProfile AMD IBS support (EXPERIMENTAL)"
+ default n
+ depends on OPROFILE && SMP && X86
+ help
+ Instruction-Based Sampling (IBS) is a new profiling
+ technique that provides rich, precise program performance
+ information. IBS is introduced by AMD Family10h processors
+ (AMD Opteron Quad-Core processor “Barcelona”) to overcome
+ the limitations of conventional performance counter
+ sampling.
+
+ If unsure, say N.
+
config HAVE_OPROFILE
def_bool n
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index f88bd0d982b..0ff576d026a 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -646,6 +646,9 @@ int setup_profiling_timer(unsigned int multiplier)
*
* Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
* MCE interrupts are supported. Thus MCE offset must be set to 0.
+ *
+ * If mask=1, the LVT entry does not generate interrupts while mask=0
+ * enables the vector. See also the BKDGs.
*/
#define APIC_EILVT_LVTOFF_MCE 0
@@ -669,6 +672,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
return APIC_EILVT_LVTOFF_IBS;
}
+EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
/*
* Local APIC start and shutdown
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 446c062e831..57744f4a75b 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -204,6 +204,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
*
* Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
* MCE interrupts are supported. Thus MCE offset must be set to 0.
+ *
+ * If mask=1, the LVT entry does not generate interrupts while mask=0
+ * enables the vector. See also the BKDGs.
*/
#define APIC_EILVT_LVTOFF_MCE 0
@@ -228,6 +231,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
return APIC_EILVT_LVTOFF_IBS;
}
+EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
/*
* Program the next event, relative to now
diff --git a/arch/x86/oprofile/Makefile b/arch/x86/oprofile/Makefile
index 30f3eb36666..446902b2a6b 100644
--- a/arch/x86/oprofile/Makefile
+++ b/arch/x86/oprofile/Makefile
@@ -7,6 +7,6 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
timer_int.o )
oprofile-y := $(DRIVER_OBJS) init.o backtrace.o
-oprofile-$(CONFIG_X86_LOCAL_APIC) += nmi_int.o op_model_athlon.o \
+oprofile-$(CONFIG_X86_LOCAL_APIC) += nmi_int.o op_model_amd.o \
op_model_ppro.o op_model_p4.o
oprofile-$(CONFIG_X86_IO_APIC) += nmi_timer_int.o
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 0227694f7da..d9885741074 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -1,10 +1,11 @@
/**
* @file nmi_int.c
*
- * @remark Copyright 2002 OProfile authors
+ * @remark Copyright 2002-2008 OProfile authors
* @remark Read the file COPYING
*
* @author John Levon <levon@movementarian.org>
+ * @author Robert Richter <robert.richter@amd.com>
*/
#include <linux/init.h>
@@ -437,6 +438,7 @@ int __init op_nmi_init(struct oprofile_operations *ops)
__u8 vendor = boot_cpu_data.x86_vendor;
__u8 family = boot_cpu_data.x86;
char *cpu_type;
+ int ret = 0;
if (!cpu_has_apic)
return -ENODEV;
@@ -449,19 +451,23 @@ int __init op_nmi_init(struct oprofile_operations *ops)
default:
return -ENODEV;
case 6:
- model = &op_athlon_spec;
+ model = &op_amd_spec;
cpu_type = "i386/athlon";
break;
case 0xf:
- model = &op_athlon_spec;
+ model = &op_amd_spec;
/* Actually it could be i386/hammer too, but give
user space an consistent name. */
cpu_type = "x86-64/hammer";
break;
case 0x10:
- model = &op_athlon_spec;
+ model = &op_amd_spec;
cpu_type = "x86-64/family10";
break;
+ case 0x11:
+ model = &op_amd_spec;
+ cpu_type = "x86-64/family11h";
+ break;
}
break;
@@ -488,17 +494,24 @@ int __init op_nmi_init(struct oprofile_operations *ops)
return -ENODEV;
}
- init_sysfs();
#ifdef CONFIG_SMP
register_cpu_notifier(&oprofile_cpu_nb);
#endif
- using_nmi = 1;
+ /* default values, can be overwritten by model */
ops->create_files = nmi_create_files;
ops->setup = nmi_setup;
ops->shutdown = nmi_shutdown;
ops->start = nmi_start;
ops->stop = nmi_stop;
ops->cpu_type = cpu_type;
+
+ if (model->init)
+ ret = model->init(ops);
+ if (ret)
+ return ret;
+
+ init_sysfs();
+ using_nmi = 1;
printk(KERN_INFO "oprofile: using NMI interrupt.\n");
return 0;
}
@@ -511,4 +524,6 @@ void op_nmi_exit(void)
unregister_cpu_notifier(&oprofile_cpu_nb);
#endif
}
+ if (model->exit)
+ model->exit();
}
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
new file mode 100644
index 00000000000..d9faf607b3a
--- /dev/null
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -0,0 +1,543 @@
+/*
+ * @file op_model_amd.c
+ * athlon / K7 / K8 / Family 10h model-specific MSR operations
+ *
+ * @remark Copyright 2002-2008 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author John Levon
+ * @author Philippe Elie
+ * @author Graydon Hoare
+ * @author Robert Richter <robert.richter@amd.com>
+ * @author Barry Kasindorf
+*/
+
+#include <linux/oprofile.h>
+#include <linux/device.h>
+#include <linux/pci.h>
+
+#include <asm/ptrace.h>
+#include <asm/msr.h>
+#include <asm/nmi.h>
+
+#include "op_x86_model.h"
+#include "op_counter.h"
+
+#define NUM_COUNTERS 4
+#define NUM_CONTROLS 4
+
+#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
+#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0)
+#define CTR_WRITE(l, msrs, c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1); } while (0)
+#define CTR_OVERFLOWED(n) (!((n) & (1U<<31)))
+
+#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
+#define CTRL_READ(l, h, msrs, c) do {rdmsr(msrs->controls[(c)].addr, (l), (h)); } while (0)
+#define CTRL_WRITE(l, h, msrs, c) do {wrmsr(msrs->controls[(c)].addr, (l), (h)); } while (0)
+#define CTRL_SET_ACTIVE(n) (n |= (1<<22))
+#define CTRL_SET_INACTIVE(n) (n &= ~(1<<22))
+#define CTRL_CLEAR_LO(x) (x &= (1<<21))
+#define CTRL_CLEAR_HI(x) (x &= 0xfffffcf0)
+#define CTRL_SET_ENABLE(val) (val |= 1<<20)
+#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16))
+#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17))
+#define CTRL_SET_UM(val, m) (val |= (m << 8))
+#define CTRL_SET_EVENT_LOW(val, e) (val |= (e & 0xff))
+#define CTRL_SET_EVENT_HIGH(val, e) (val |= ((e >> 8) & 0xf))
+#define CTRL_SET_HOST_ONLY(val, h) (val |= ((h & 1) << 9))
+#define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8))
+
+static unsigned long reset_value[NUM_COUNTERS];
+
+#ifdef CONFIG_OPROFILE_IBS
+
+/* IbsFetchCtl bits/masks */
+#define IBS_FETCH_HIGH_VALID_BIT (1UL << 17) /* bit 49 */
+#define IBS_FETCH_HIGH_ENABLE (1UL << 16) /* bit 48 */
+#define IBS_FETCH_LOW_MAX_CNT_MASK 0x0000FFFFUL /* MaxCnt mask */
+
+/*IbsOpCtl bits */
+#define IBS_OP_LOW_VALID_BIT (1ULL<<18) /* bit 18 */
+#define IBS_OP_LOW_ENABLE (1ULL<<17) /* bit 17 */
+
+/* Codes used in cpu_buffer.c */
+/* This produces duplicate code, need to be fixed */
+#define IBS_FETCH_BEGIN 3
+#define IBS_OP_BEGIN 4
+
+/* The function interface needs to be fixed, something like add
+ data. Should then be added to linux/oprofile.h. */
+extern void oprofile_add_ibs_sample(struct pt_regs *const regs,
+ unsigned int * const ibs_sample, u8 code);
+
+struct ibs_fetch_sample {
+ /* MSRC001_1031 IBS Fetch Linear Address Register */
+ unsigned int ibs_fetch_lin_addr_low;
+ unsigned int ibs_fetch_lin_addr_high;
+ /* MSRC001_1030 IBS Fetch Control Register */
+ unsigned int ibs_fetch_ctl_low;
+ unsigned int ibs_fetch_ctl_high;
+ /* MSRC001_1032 IBS Fetch Physical Address Register */
+ unsigned int ibs_fetch_phys_addr_low;
+ unsigned int ibs_fetch_phys_addr_high;
+};
+
+struct ibs_op_sample {
+ /* MSRC001_1034 IBS Op Logical Address Register (IbsRIP) */
+ unsigned int ibs_op_rip_low;
+ unsigned int ibs_op_rip_high;
+ /* MSRC001_1035 IBS Op Data Register */
+ unsigned int ibs_op_data1_low;
+ unsigned int ibs_op_data1_high;
+ /* MSRC001_1036 IBS Op Data 2 Register */
+ unsigned int ibs_op_data2_low;
+ unsigned int ibs_op_data2_high;
+ /* MSRC001_1037 IBS Op Data 3 Register */
+ unsigned int ibs_op_data3_low;
+ unsigned int ibs_op_data3_high;
+ /* MSRC001_1038 IBS DC Linear Address Register (IbsDcLinAd) */
+ unsigned int ibs_dc_linear_low;
+ unsigned int ibs_dc_linear_high;
+ /* MSRC001_1039 IBS DC Physical Address Register (IbsDcPhysAd) */
+ unsigned int ibs_dc_phys_low;
+ unsigned int ibs_dc_phys_high;
+};
+
+/*
+ * unitialize the APIC for the IBS interrupts if needed on AMD Family10h+
+*/
+static void clear_ibs_nmi(void);
+
+static int ibs_allowed; /* AMD Family10h and later */
+
+struct op_ibs_config {
+ unsigned long op_enabled;
+ unsigned long fetch_enabled;
+ unsigned long max_cnt_fetch;
+ unsigned long max_cnt_op;
+ unsigned long rand_en;
+ unsigned long dispatched_ops;
+};
+
+static struct op_ibs_config ibs_config;
+
+#endif
+
+/* functions for op_amd_spec */
+
+static void op_amd_fill_in_addresses(struct op_msrs * const msrs)
+{
+ int i;
+
+ for (i = 0; i < NUM_COUNTERS; i++) {
+ if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
+ msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
+ else
+ msrs->counters[i].addr = 0;
+ }
+
+ for (i = 0; i < NUM_CONTROLS; i++) {
+ if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i))
+ msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
+ else
+ msrs->controls[i].addr = 0;
+ }
+}
+
+
+static void op_amd_setup_ctrs(struct op_msrs const * const msrs)
+{
+ unsigned int low, high;
+ int i;
+
+ /* clear all counters */
+ for (i = 0 ; i < NUM_CONTROLS; ++i) {
+ if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
+ continue;
+ CTRL_READ(low, high, msrs, i);
+ CTRL_CLEAR_LO(low);
+ CTRL_CLEAR_HI(high);
+ CTRL_WRITE(low, high, msrs, i);
+ }
+
+ /* avoid a false detection of ctr overflows in NMI handler */
+ for (i = 0; i < NUM_COUNTERS; ++i) {
+ if (unlikely(!CTR_IS_RESERVED(msrs, i)))
+ continue;
+ CTR_WRITE(1, msrs, i);
+ }
+
+ /* enable active counters */
+ for (i = 0; i < NUM_COUNTERS; ++i) {
+ if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) {
+ reset_value[i] = counter_config[i].count;
+
+ CTR_WRITE(counter_config[i].count, msrs, i);
+
+ CTRL_READ(low, high, msrs, i);
+ CTRL_CLEAR_LO(low);
+ CTRL_CLEAR_HI(high);
+ CTRL_SET_ENABLE(low);
+ CTRL_SET_USR(low, counter_config[i].user);
+ CTRL_SET_KERN(low, counter_config[i].kernel);
+ CTRL_SET_UM(low, counter_config[i].unit_mask);
+ CTRL_SET_EVENT_LOW(low, counter_config[i].event);
+ CTRL_SET_EVENT_HIGH(high, counter_config[i].event);
+ CTRL_SET_HOST_ONLY(high, 0);
+ CTRL_SET_GUEST_ONLY(high, 0);
+
+ CTRL_WRITE(low, high, msrs, i);
+ } else {
+ reset_value[i] = 0;
+ }
+ }
+}
+
+#ifdef CONFIG_OPROFILE_IBS
+
+static inline int
+op_amd_handle_ibs(struct pt_regs * const regs,
+ struct op_msrs const * const msrs)
+{
+ unsigned int low, high;
+ struct ibs_fetch_sample ibs_fetch;
+ struct ibs_op_sample ibs_op;
+
+ if (!ibs_allowed)
+ return 1;
+
+ if (ibs_config.fetch_enabled) {
+ rdmsr(MSR_AMD64_IBSFETCHCTL, low, high);
+ if (high & IBS_FETCH_HIGH_VALID_BIT) {
+ ibs_fetch.ibs_fetch_ctl_high = high;
+ ibs_fetch.ibs_fetch_ctl_low = low;
+ rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high);
+ ibs_fetch.ibs_fetch_lin_addr_high = high;
+ ibs_fetch.ibs_fetch_lin_addr_low = low;
+ rdmsr(MSR_AMD64_IBSFETCHPHYSAD, low, high);
+ ibs_fetch.ibs_fetch_phys_addr_high = high;
+ ibs_fetch.ibs_fetch_phys_addr_low = low;
+
+ oprofile_add_ibs_sample(regs,
+ (unsigned int *)&ibs_fetch,
+ IBS_FETCH_BEGIN);
+
+ /*reenable the IRQ */
+ rdmsr(MSR_AMD64_IBSFETCHCTL, low, high);
+ high &= ~IBS_FETCH_HIGH_VALID_BIT;
+ high |= IBS_FETCH_HIGH_ENABLE;
+ low &= IBS_FETCH_LOW_MAX_CNT_MASK;
+ wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
+ }
+ }
+
+ if (ibs_config.op_enabled) {
+ rdmsr(MSR_AMD64_IBSOPCTL, low, high);
+ if (low & IBS_OP_LOW_VALID_BIT) {
+ rdmsr(MSR_AMD64_IBSOPRIP, low, high);
+ ibs_op.ibs_op_rip_low = low;
+ ibs_op.ibs_op_rip_high = high;
+ rdmsr(MSR_AMD64_IBSOPDATA, low, high);
+ ibs_op.ibs_op_data1_low = low;
+ ibs_op.ibs_op_data1_high = high;
+ rdmsr(MSR_AMD64_IBSOPDATA2, low, high);
+ ibs_op.ibs_op_data2_low = low;
+ ibs_op.ibs_op_data2_high = high;
+ rdmsr(MSR_AMD64_IBSOPDATA3, low, high);
+ ibs_op.ibs_op_data3_low = low;
+ ibs_op.ibs_op_data3_high = high;
+ rdmsr(MSR_AMD64_IBSDCLINAD, low, high);
+ ibs_op.ibs_dc_linear_low = low;
+ ibs_op.ibs_dc_linear_high = high;
+ rdmsr(MSR_AMD64_IBSDCPHYSAD, low, high);
+ ibs_op.ibs_dc_phys_low = low;
+ ibs_op.ibs_dc_phys_high = high;
+
+ /* reenable the IRQ */
+ oprofile_add_ibs_sample(regs,
+ (unsigned int *)&ibs_op,
+ IBS_OP_BEGIN);
+ rdmsr(MSR_AMD64_IBSOPCTL, low, high);
+ high = 0;
+ low &= ~IBS_OP_LOW_VALID_BIT;
+ low |= IBS_OP_LOW_ENABLE;
+ wrmsr(MSR_AMD64_IBSOPCTL, low, high);
+ }
+ }
+
+ return 1;
+}
+
+#endif
+
+static int op_amd_check_ctrs(struct pt_regs * const regs,
+ struct op_msrs const * const msrs)
+{
+ unsigned int low, high;
+ int i;
+
+ for (i = 0 ; i < NUM_COUNTERS; ++i) {
+ if (!reset_value[i])
+ continue;
+ CTR_READ(low, high, msrs, i);
+ if (CTR_OVERFLOWED(low)) {
+ oprofile_add_sample(regs, i);
+ CTR_WRITE(reset_value[i], msrs, i);
+ }
+ }
+
+#ifdef CONFIG_OPROFILE_IBS
+ op_amd_handle_ibs(regs, msrs);
+#endif
+
+ /* See op_model_ppro.c */
+ return 1;
+}
+
+static void op_amd_start(struct op_msrs const * const msrs)
+{
+ unsigned int low, high;
+ int i;
+ for (i = 0 ; i < NUM_COUNTERS ; ++i) {
+ if (reset_value[i]) {
+ CTRL_READ(low, high, msrs, i);
+ CTRL_SET_ACTIVE(low);
+ CTRL_WRITE(low, high, msrs, i);
+ }
+ }
+
+#ifdef CONFIG_OPROFILE_IBS
+ if (ibs_allowed && ibs_config.fetch_enabled) {
+ low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF;
+ high = IBS_FETCH_HIGH_ENABLE;
+ wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
+ }
+
+ if (ibs_allowed && ibs_config.op_enabled) {
+ low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + IBS_OP_LOW_ENABLE;
+ high = 0;
+ wrmsr(MSR_AMD64_IBSOPCTL, low, high);
+ }
+#endif
+}
+
+
+static void op_amd_stop(struct op_msrs const * const msrs)
+{
+ unsigned int low, high;
+ int i;
+
+ /* Subtle: stop on all counters to avoid race with
+ * setting our pm callback */
+ for (i = 0 ; i < NUM_COUNTERS ; ++i) {
+ if (!reset_value[i])
+ continue;
+ CTRL_READ(low, high, msrs, i);
+ CTRL_SET_INACTIVE(low);
+ CTRL_WRITE(low, high, msrs, i);
+ }
+
+#ifdef CONFIG_OPROFILE_IBS
+ if (ibs_allowed && ibs_config.fetch_enabled) {
+ low = 0; /* clear max count and enable */
+ high = 0;
+ wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
+ }
+
+ if (ibs_allowed && ibs_config.op_enabled) {
+ low = 0; /* clear max count and enable */
+ high = 0;
+ wrmsr(MSR_AMD64_IBSOPCTL, low, high);
+ }
+#endif
+}
+
+static void op_amd_shutdown(struct op_msrs const * const msrs)
+{
+ int i;
+
+ for (i = 0 ; i < NUM_COUNTERS ; ++i) {
+ if (CTR_IS_RESERVED(msrs, i))
+ release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+ }
+ for (i = 0 ; i < NUM_CONTROLS ; ++i) {
+ if (CTRL_IS_RESERVED(msrs, i))
+ release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+ }
+}
+
+#ifndef CONFIG_OPROFILE_IBS
+
+/* no IBS support */
+
+static int op_amd_init(struct oprofile_operations *ops)
+{
+ return 0;
+}
+
+static void op_amd_exit(void) {}
+
+#else
+
+static u8 ibs_eilvt_off;
+
+static inline void apic_init_ibs_nmi_per_cpu(void *arg)
+{
+ ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0);
+}
+
+static inline void apic_clear_ibs_nmi_per_cpu(void *arg)
+{
+ setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
+}
+
+static int pfm_amd64_setup_eilvt(void)
+{
+#define IBSCTL_LVTOFFSETVAL (1 << 8)
+#define IBSCTL 0x1cc
+ struct pci_dev *cpu_cfg;
+ int nodes;
+ u32 value = 0;
+
+ /* per CPU setup */
+ on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1);
+
+ nodes = 0;
+ cpu_cfg = NULL;
+ do {
+ cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD,
+ PCI_DEVICE_ID_AMD_10H_NB_MISC,
+ cpu_cfg);
+ if (!cpu_cfg)
+ break;
+ ++nodes;
+ pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off
+ | IBSCTL_LVTOFFSETVAL);
+ pci_read_config_dword(cpu_cfg, IBSCTL, &value);
+ if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) {
+ printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
+ "IBSCTL = 0x%08x", value);
+ return 1;
+ }
+ } while (1);
+
+ if (!nodes) {
+ printk(KERN_DEBUG "No CPU node configured for IBS");
+ return 1;
+ }
+
+#ifdef CONFIG_NUMA
+ /* Sanity check */
+ /* Works only for 64bit with proper numa implementation. */
+ if (nodes != num_possible_nodes()) {
+ printk(KERN_DEBUG "Failed to setup CPU node(s) for IBS, "
+ "found: %d, expected %d",
+ nodes, num_possible_nodes());
+ return 1;
+ }
+#endif
+ return 0;
+}
+
+/*
+ * initialize the APIC for the IBS interrupts
+ * if available (AMD Family10h rev B0 and later)
+ */
+static void setup_ibs(void)
+{
+ ibs_allowed = boot_cpu_has(X86_FEATURE_IBS);
+
+ if (!ibs_allowed)
+ return;
+
+ if (pfm_amd64_setup_eilvt()) {
+ ibs_allowed = 0;
+ return;
+ }
+
+ printk(KERN_INFO "oprofile: AMD IBS detected\n");
+}
+
+
+/*
+ * unitialize the APIC for the IBS interrupts if needed on AMD Family10h
+ * rev B0 and later */
+static void clear_ibs_nmi(void)
+{
+ if (ibs_allowed)
+ on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1);
+}
+
+static int (*create_arch_files)(struct super_block * sb, struct dentry * root);
+
+static int setup_ibs_files(struct super_block * sb, struct dentry * root)
+{
+ char buf[12];
+ struct dentry *dir;
+ int ret = 0;
+
+ /* architecture specific files */
+ if (create_arch_files)
+ ret = create_arch_files(sb, root);
+
+ if (ret)
+ return ret;
+
+ if (!ibs_allowed)
+ return ret;
+
+ /* model specific files */
+
+ /* setup some reasonable defaults */
+ ibs_config.max_cnt_fetch = 250000;
+ ibs_config.fetch_enabled = 0;
+ ibs_config.max_cnt_op = 250000;
+ ibs_config.op_enabled = 0;
+ ibs_config.dispatched_ops = 1;
+ snprintf(buf, sizeof(buf), "ibs_fetch");
+ dir = oprofilefs_mkdir(sb, root, buf);
+ oprofilefs_create_ulong(sb, dir, "rand_enable",
+ &ibs_config.rand_en);
+ oprofilefs_create_ulong(sb, dir, "enable",
+ &ibs_config.fetch_enabled);
+ oprofilefs_create_ulong(sb, dir, "max_count",
+ &ibs_config.max_cnt_fetch);
+ snprintf(buf, sizeof(buf), "ibs_uops");
+ dir = oprofilefs_mkdir(sb, root, buf);
+ oprofilefs_create_ulong(sb, dir, "enable",
+ &ibs_config.op_enabled);
+ oprofilefs_create_ulong(sb, dir, "max_count",
+ &ibs_config.max_cnt_op);
+ oprofilefs_create_ulong(sb, dir, "dispatched_ops",
+ &ibs_config.dispatched_ops);
+
+ return 0;
+}
+
+static int op_amd_init(struct oprofile_operations *ops)
+{
+ setup_ibs();
+ create_arch_files = ops->create_files;
+ ops->create_files = setup_ibs_files;
+ return 0;
+}
+
+static void op_amd_exit(void)
+{
+ clear_ibs_nmi();
+}
+
+#endif
+
+struct op_x86_model_spec const op_amd_spec = {
+ .init = op_amd_init,
+ .exit = op_amd_exit,
+ .num_counters = NUM_COUNTERS,
+ .num_controls = NUM_CONTROLS,
+ .fill_in_addresses = &op_amd_fill_in_addresses,
+ .setup_ctrs = &op_amd_setup_ctrs,
+ .check_ctrs = &op_amd_check_ctrs,
+ .start = &op_amd_start,
+ .stop = &op_amd_stop,
+ .shutdown = &op_amd_shutdown
+};
diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c
deleted file mode 100644
index 3d534879a9d..00000000000
--- a/arch/x86/oprofile/op_model_athlon.c
+++ /dev/null
@@ -1,190 +0,0 @@
-/*
- * @file op_model_athlon.h
- * athlon / K7 / K8 / Family 10h model-specific MSR operations
- *
- * @remark Copyright 2002 OProfile authors
- * @remark Read the file COPYING
- *
- * @author John Levon
- * @author Philippe Elie
- * @author Graydon Hoare
- */
-
-#include <linux/oprofile.h>
-#include <asm/ptrace.h>
-#include <asm/msr.h>
-#include <asm/nmi.h>
-
-#include "op_x86_model.h"
-#include "op_counter.h"
-
-#define NUM_COUNTERS 4
-#define NUM_CONTROLS 4
-
-#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
-#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0)
-#define CTR_WRITE(l, msrs, c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1); } while (0)
-#define CTR_OVERFLOWED(n) (!((n) & (1U<<31)))
-
-#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
-#define CTRL_READ(l, h, msrs, c) do {rdmsr(msrs->controls[(c)].addr, (l), (h)); } while (0)
-#define CTRL_WRITE(l, h, msrs, c) do {wrmsr(msrs->controls[(c)].addr, (l), (h)); } while (0)
-#define CTRL_SET_ACTIVE(n) (n |= (1<<22))
-#define CTRL_SET_INACTIVE(n) (n &= ~(1<<22))
-#define CTRL_CLEAR_LO(x) (x &= (1<<21))
-#define CTRL_CLEAR_HI(x) (x &= 0xfffffcf0)
-#define CTRL_SET_ENABLE(val) (val |= 1<<20)
-#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16))
-#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17))
-#define CTRL_SET_UM(val, m) (val |= (m << 8))
-#define CTRL_SET_EVENT_LOW(val, e) (val |= (e & 0xff))
-#define CTRL_SET_EVENT_HIGH(val, e) (val |= ((e >> 8) & 0xf))
-#define CTRL_SET_HOST_ONLY(val, h) (val |= ((h & 1) << 9))
-#define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8))
-
-static unsigned long reset_value[NUM_COUNTERS];
-
-static void athlon_fill_in_addresses(struct op_msrs * const msrs)
-{
- int i;
-
- for (i = 0; i < NUM_COUNTERS; i++) {
- if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
- msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
- else
- msrs->counters[i].addr = 0;
- }
-
- for (i = 0; i < NUM_CONTROLS; i++) {
- if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i))
- msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
- else
- msrs->controls[i].addr = 0;
- }
-}
-
-
-static void athlon_setup_ctrs(struct op_msrs const * const msrs)
-{
- unsigned int low, high;
- int i;
-
- /* clear all counters */
- for (i = 0 ; i < NUM_CONTROLS; ++i) {
- if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
- continue;
- CTRL_READ(low, high, msrs, i);
- CTRL_CLEAR_LO(low);
- CTRL_CLEAR_HI(high);
- CTRL_WRITE(low, high, msrs, i);
- }
-
- /* avoid a false detection of ctr overflows in NMI handler */
- for (i = 0; i < NUM_COUNTERS; ++i) {
- if (unlikely(!CTR_IS_RESERVED(msrs, i)))
- continue;
- CTR_WRITE(1, msrs, i);
- }
-
- /* enable active counters */
- for (i = 0; i < NUM_COUNTERS; ++i) {
- if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) {
- reset_value[i] = counter_config[i].count;
-
- CTR_WRITE(counter_config[i].count, msrs, i);
-
- CTRL_READ(low, high, msrs, i);
- CTRL_CLEAR_LO(low);
- CTRL_CLEAR_HI(high);
- CTRL_SET_ENABLE(low);
- CTRL_SET_USR(low, counter_config[i].user);
- CTRL_SET_KERN(low, counter_config[i].kernel);
- CTRL_SET_UM(low, counter_config[i].unit_mask);
- CTRL_SET_EVENT_LOW(low, counter_config[i].event);
- CTRL_SET_EVENT_HIGH(high, counter_config[i].event);
- CTRL_SET_HOST_ONLY(high, 0);
- CTRL_SET_GUEST_ONLY(high, 0);
-
- CTRL_WRITE(low, high, msrs, i);
- } else {
- reset_value[i] = 0;
- }
- }
-}
-
-
-static int athlon_check_ctrs(struct pt_regs * const regs,
- struct op_msrs const * const msrs)
-{
- unsigned int low, high;
- int i;
-
- for (i = 0 ; i < NUM_COUNTERS; ++i) {
- if (!reset_value[i])
- continue;
- CTR_READ(low, high, msrs, i);
- if (CTR_OVERFLOWED(low)) {
- oprofile_add_sample(regs, i);
- CTR_WRITE(reset_value[i], msrs, i);
- }
- }
-
- /* See op_model_ppro.c */
- return 1;
-}
-
-
-static void athlon_start(struct op_msrs const * const msrs)
-{
- unsigned int low, high;
- int i;
- for (i = 0 ; i < NUM_COUNTERS ; ++i) {
- if (reset_value[i]) {
- CTRL_READ(low, high, msrs, i);
- CTRL_SET_ACTIVE(low);
- CTRL_WRITE(low, high, msrs, i);
- }
- }
-}
-
-
-static void athlon_stop(struct op_msrs const * const msrs)
-{
- unsigned int low, high;
- int i;
-
- /* Subtle: stop on all counters to avoid race with
- * setting our pm callback */
- for (i = 0 ; i < NUM_COUNTERS ; ++i) {
- if (!reset_value[i])
- continue;
- CTRL_READ(low, high, msrs, i);
- CTRL_SET_INACTIVE(low);
- CTRL_WRITE(low, high, msrs, i);
- }
-}
-
-static void athlon_shutdown(struct op_msrs const * const msrs)
-{
- int i;
-
- for (i = 0 ; i < NUM_COUNTERS ; ++i) {
- if (CTR_IS_RESERVED(msrs, i))
- release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
- }
- for (i = 0 ; i < NUM_CONTROLS ; ++i) {
- if (CTRL_IS_RESERVED(msrs, i))
- release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
- }
-}
-
-struct op_x86_model_spec const op_athlon_spec = {
- .num_counters = NUM_COUNTERS,
- .num_controls = NUM_CONTROLS,
- .fill_in_addresses = &athlon_fill_in_addresses,
- .setup_ctrs = &athlon_setup_ctrs,
- .check_ctrs = &athlon_check_ctrs,
- .start = &athlon_start,
- .stop = &athlon_stop,
- .shutdown = &athlon_shutdown
-};
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 56b4757a1f4..43ac5af338d 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -10,11 +10,12 @@
#include <linux/oprofile.h>
#include <linux/smp.h>
+#include <linux/ptrace.h>
+#include <linux/nmi.h>
#include <asm/msr.h>
-#include <asm/ptrace.h>
#include <asm/fixmap.h>
#include <asm/apic.h>
-#include <asm/nmi.h>
+
#include "op_x86_model.h"
#include "op_counter.h"
@@ -40,7 +41,7 @@ static unsigned int num_controls = NUM_CONTROLS_NON_HT;
static inline void setup_num_counters(void)
{
#ifdef CONFIG_SMP
- if (smp_num_siblings == 2){
+ if (smp_num_siblings == 2) {
num_counters = NUM_COUNTERS_HT2;
num_controls = NUM_CONTROLS_HT2;
}
@@ -86,7 +87,7 @@ struct p4_event_binding {
#define CTR_FLAME_2 (1 << 6)
#define CTR_IQ_5 (1 << 7)
-static struct p4_counter_binding p4_counters [NUM_COUNTERS_NON_HT] = {
+static struct p4_counter_binding p4_counters[NUM_COUNTERS_NON_HT] = {
{ CTR_BPU_0, MSR_P4_BPU_PERFCTR0, MSR_P4_BPU_CCCR0 },
{ CTR_MS_0, MSR_P4_MS_PERFCTR0, MSR_P4_MS_CCCR0 },
{ CTR_FLAME_0, MSR_P4_FLAME_PERFCTR0, MSR_P4_FLAME_CCCR0 },
@@ -97,32 +98,32 @@ static struct p4_counter_binding p4_counters [NUM_COUNTERS_NON_HT] = {
{ CTR_IQ_5, MSR_P4_IQ_PERFCTR5, MSR_P4_IQ_CCCR5 }
};
-#define NUM_UNUSED_CCCRS NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT
+#define NUM_UNUSED_CCCRS (NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT)
/* p4 event codes in libop/op_event.h are indices into this table. */
static struct p4_event_binding p4_events[NUM_EVENTS] = {
-
+
{ /* BRANCH_RETIRED */
- 0x05, 0x06,
+ 0x05, 0x06,
{ {CTR_IQ_4, MSR_P4_CRU_ESCR2},
{CTR_IQ_5, MSR_P4_CRU_ESCR3} }
},
-
+
{ /* MISPRED_BRANCH_RETIRED */
- 0x04, 0x03,
+ 0x04, 0x03,
{ { CTR_IQ_4, MSR_P4_CRU_ESCR0},
{ CTR_IQ_5, MSR_P4_CRU_ESCR1} }
},
-
+
{ /* TC_DELIVER_MODE */
0x01, 0x01,
- { { CTR_MS_0, MSR_P4_TC_ESCR0},
+ { { CTR_MS_0, MSR_P4_TC_ESCR0},
{ CTR_MS_2, MSR_P4_TC_ESCR1} }
},
-
+
{ /* BPU_FETCH_REQUEST */
- 0x00, 0x03,
+ 0x00, 0x03,
{ { CTR_BPU_0, MSR_P4_BPU_ESCR0},
{ CTR_BPU_2, MSR_P4_BPU_ESCR1} }
},
@@ -146,7 +147,7 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
},
{ /* LOAD_PORT_REPLAY */
- 0x02, 0x04,
+ 0x02, 0x04,
{ { CTR_FLAME_0, MSR_P4_SAAT_ESCR0},
{ CTR_FLAME_2, MSR_P4_SAAT_ESCR1} }
},
@@ -170,43 +171,43 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
},
{ /* BSQ_CACHE_REFERENCE */
- 0x07, 0x0c,
+ 0x07, 0x0c,
{ { CTR_BPU_0, MSR_P4_BSU_ESCR0},
{ CTR_BPU_2, MSR_P4_BSU_ESCR1} }
},
{ /* IOQ_ALLOCATION */
- 0x06, 0x03,
+ 0x06, 0x03,
{ { CTR_BPU_0, MSR_P4_FSB_ESCR0},
{ 0, 0 } }
},
{ /* IOQ_ACTIVE_ENTRIES */
- 0x06, 0x1a,
+ 0x06, 0x1a,
{ { CTR_BPU_2, MSR_P4_FSB_ESCR1},
{ 0, 0 } }
},
{ /* FSB_DATA_ACTIVITY */
- 0x06, 0x17,
+ 0x06, 0x17,
{ { CTR_BPU_0, MSR_P4_FSB_ESCR0},
{ CTR_BPU_2, MSR_P4_FSB_ESCR1} }
},
{ /* BSQ_ALLOCATION */
- 0x07, 0x05,
+ 0x07, 0x05,
{ { CTR_BPU_0, MSR_P4_BSU_ESCR0},
{ 0, 0 } }
},
{ /* BSQ_ACTIVE_ENTRIES */
0x07, 0x06,
- { { CTR_BPU_2, MSR_P4_BSU_ESCR1 /* guess */},
+ { { CTR_BPU_2, MSR_P4_BSU_ESCR1 /* guess */},
{ 0, 0 } }
},
{ /* X87_ASSIST */
- 0x05, 0x03,
+ 0x05, 0x03,
{ { CTR_IQ_4, MSR_P4_CRU_ESCR2},
{ CTR_IQ_5, MSR_P4_CRU_ESCR3} }
},
@@ -216,21 +217,21 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
{ CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
},
-
+
{ /* PACKED_SP_UOP */
- 0x01, 0x08,
+ 0x01, 0x08,
{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
{ CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
},
-
+
{ /* PACKED_DP_UOP */
- 0x01, 0x0c,
+ 0x01, 0x0c,
{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
{ CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
},
{ /* SCALAR_SP_UOP */
- 0x01, 0x0a,
+ 0x01, 0x0a,
{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
{ CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
},
@@ -242,31 +243,31 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
},
{ /* 64BIT_MMX_UOP */
- 0x01, 0x02,
+ 0x01, 0x02,
{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
{ CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
},
-
+
{ /* 128BIT_MMX_UOP */
- 0x01, 0x1a,
+ 0x01, 0x1a,
{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
{ CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
},
{ /* X87_FP_UOP */
- 0x01, 0x04,
+ 0x01, 0x04,
{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
{ CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
},
-
+
{ /* X87_SIMD_MOVES_UOP */
- 0x01, 0x2e,
+ 0x01, 0x2e,
{ { CTR_FLAME_0, MSR_P4_FIRM_ESCR0},
{ CTR_FLAME_2, MSR_P4_FIRM_ESCR1} }
},
-
+
{ /* MACHINE_CLEAR */
- 0x05, 0x02,
+ 0x05, 0x02,
{ { CTR_IQ_4, MSR_P4_CRU_ESCR2},
{ CTR_IQ_5, MSR_P4_CRU_ESCR3} }
},
@@ -276,9 +277,9 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
{ { CTR_BPU_0, MSR_P4_FSB_ESCR0},
{ CTR_BPU_2, MSR_P4_FSB_ESCR1} }
},
-
+
{ /* TC_MS_XFER */
- 0x00, 0x05,
+ 0x00, 0x05,
{ { CTR_MS_0, MSR_P4_MS_ESCR0},
{ CTR_MS_2, MSR_P4_MS_ESCR1} }
},
@@ -308,7 +309,7 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
},
{ /* INSTR_RETIRED */
- 0x04, 0x02,
+ 0x04, 0x02,
{ { CTR_IQ_4, MSR_P4_CRU_ESCR0},
{ CTR_IQ_5, MSR_P4_CRU_ESCR1} }
},
@@ -319,14 +320,14 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
{ CTR_IQ_5, MSR_P4_CRU_ESCR1} }
},
- { /* UOP_TYPE */
- 0x02, 0x02,
+ { /* UOP_TYPE */
+ 0x02, 0x02,
{ { CTR_IQ_4, MSR_P4_RAT_ESCR0},
{ CTR_IQ_5, MSR_P4_RAT_ESCR1} }
},
{ /* RETIRED_MISPRED_BRANCH_TYPE */
- 0x02, 0x05,
+ 0x02, 0x05,
{ { CTR_MS_0, MSR_P4_TBPU_ESCR0},
{ CTR_MS_2, MSR_P4_TBPU_ESCR1} }
},
@@ -349,8 +350,8 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
#define ESCR_SET_OS_1(escr, os) ((escr) |= (((os) & 1) << 1))
#define ESCR_SET_EVENT_SELECT(escr, sel) ((escr) |= (((sel) & 0x3f) << 25))
#define ESCR_SET_EVENT_MASK(escr, mask) ((escr) |= (((mask) & 0xffff) << 9))
-#define ESCR_READ(escr,high,ev,i) do {rdmsr(ev->bindings[(i)].escr_address, (escr), (high));} while (0)
-#define ESCR_WRITE(escr,high,ev,i) do {wrmsr(ev->bindings[(i)].escr_address, (escr), (high));} while (0)
+#define ESCR_READ(escr, high, ev, i) do {rdmsr(ev->bindings[(i)].escr_address, (escr), (high)); } while (0)
+#define ESCR_WRITE(escr, high, ev, i) do {wrmsr(ev->bindings[(i)].escr_address, (escr), (high)); } while (0)
#define CCCR_RESERVED_BITS 0x38030FFF
#define CCCR_CLEAR(cccr) ((cccr) &= CCCR_RESERVED_BITS)
@@ -360,15 +361,15 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
#define CCCR_SET_PMI_OVF_1(cccr) ((cccr) |= (1<<27))
#define CCCR_SET_ENABLE(cccr) ((cccr) |= (1<<12))
#define CCCR_SET_DISABLE(cccr) ((cccr) &= ~(1<<12))
-#define CCCR_READ(low, high, i) do {rdmsr(p4_counters[(i)].cccr_address, (low), (high));} while (0)
-#define CCCR_WRITE(low, high, i) do {wrmsr(p4_counters[(i)].cccr_address, (low), (high));} while (0)
+#define CCCR_READ(low, high, i) do {rdmsr(p4_counters[(i)].cccr_address, (low), (high)); } while (0)
+#define CCCR_WRITE(low, high, i) do {wrmsr(p4_counters[(i)].cccr_address, (low), (high)); } while (0)
#define CCCR_OVF_P(cccr) ((cccr) & (1U<<31))
#define CCCR_CLEAR_OVF(cccr) ((cccr) &= (~(1U<<31)))
-#define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0)
-#define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0)
-#define CTR_READ(l,h,i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h));} while (0)
-#define CTR_WRITE(l,i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1);} while (0)
+#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
+#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
+#define CTR_READ(l, h, i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h)); } while (0)
+#define CTR_WRITE(l, i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1); } while (0)
#define CTR_OVERFLOW_P(ctr) (!((ctr) & 0x80000000))
@@ -380,7 +381,7 @@ static unsigned int get_stagger(void)
#ifdef CONFIG_SMP
int cpu = smp_processor_id();
return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu)));
-#endif
+#endif
return 0;
}
@@ -395,25 +396,23 @@ static unsigned long reset_value[NUM_COUNTERS_NON_HT];
static void p4_fill_in_addresses(struct op_msrs * const msrs)
{
- unsigned int i;
+ unsigned int i;
unsigned int addr, cccraddr, stag;
setup_num_counters();
stag = get_stagger();
/* initialize some registers */
- for (i = 0; i < num_counters; ++i) {
+ for (i = 0; i < num_counters; ++i)
msrs->counters[i].addr = 0;
- }
- for (i = 0; i < num_controls; ++i) {
+ for (i = 0; i < num_controls; ++i)
msrs->controls[i].addr = 0;
- }
-
+
/* the counter & cccr registers we pay attention to */
for (i = 0; i < num_counters; ++i) {
addr = p4_counters[VIRT_CTR(stag, i)].counter_address;
cccraddr = p4_counters[VIRT_CTR(stag, i)].cccr_address;
- if (reserve_perfctr_nmi(addr)){
+ if (reserve_perfctr_nmi(addr)) {
msrs->counters[i].addr = addr;
msrs->controls[i].addr = cccraddr;
}
@@ -447,22 +446,22 @@ static void p4_fill_in_addresses(struct op_msrs * const msrs)
if (reserve_evntsel_nmi(addr))
msrs->controls[i].addr = addr;
}
-
+
for (addr = MSR_P4_MS_ESCR0 + stag;
- addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) {
+ addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) {
if (reserve_evntsel_nmi(addr))
msrs->controls[i].addr = addr;
}
-
+
for (addr = MSR_P4_IX_ESCR0 + stag;
- addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) {
+ addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) {
if (reserve_evntsel_nmi(addr))
msrs->controls[i].addr = addr;
}
/* there are 2 remaining non-contiguously located ESCRs */
- if (num_counters == NUM_COUNTERS_NON_HT) {
+ if (num_counters == NUM_COUNTERS_NON_HT) {
/* standard non-HT CPUs handle both remaining ESCRs*/
if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR5))
msrs->controls[i++].addr = MSR_P4_CRU_ESCR5;
@@ -498,20 +497,20 @@ static void pmc_setup_one_p4_counter(unsigned int ctr)
unsigned int stag;
stag = get_stagger();
-
+
/* convert from counter *number* to counter *bit* */
counter_bit = 1 << VIRT_CTR(stag, ctr);
-
+
/* find our event binding structure. */
if (counter_config[ctr].event <= 0 || counter_config[ctr].event > NUM_EVENTS) {
- printk(KERN_ERR
- "oprofile: P4 event code 0x%lx out of range\n",
+ printk(KERN_ERR
+ "oprofile: P4 event code 0x%lx out of range\n",
counter_config[ctr].event);
return;
}
-
+
ev = &(p4_events[counter_config[ctr].event - 1]);
-
+
for (i = 0; i < maxbind; i++) {
if (ev->bindings[i].virt_counter & counter_bit) {
@@ -526,25 +525,24 @@ static void pmc_setup_one_p4_counter(unsigned int ctr)
ESCR_SET_OS_1(escr, counter_config[ctr].kernel);
}
ESCR_SET_EVENT_SELECT(escr, ev->event_select);
- ESCR_SET_EVENT_MASK(escr, counter_config[ctr].unit_mask);
+ ESCR_SET_EVENT_MASK(escr, counter_config[ctr].unit_mask);
ESCR_WRITE(escr, high, ev, i);
-
+
/* modify CCCR */
CCCR_READ(cccr, high, VIRT_CTR(stag, ctr));
CCCR_CLEAR(cccr);
CCCR_SET_REQUIRED_BITS(cccr);
CCCR_SET_ESCR_SELECT(cccr, ev->escr_select);
- if (stag == 0) {
+ if (stag == 0)
CCCR_SET_PMI_OVF_0(cccr);
- } else {
+ else
CCCR_SET_PMI_OVF_1(cccr);
- }
CCCR_WRITE(cccr, high, VIRT_CTR(stag, ctr));
return;
}
}
- printk(KERN_ERR
+ printk(KERN_ERR
"oprofile: P4 event code 0x%lx no binding, stag %d ctr %d\n",
counter_config[ctr].event, stag, ctr);
}
@@ -559,14 +557,14 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs)
stag = get_stagger();
rdmsr(MSR_IA32_MISC_ENABLE, low, high);
- if (! MISC_PMC_ENABLED_P(low)) {
+ if (!MISC_PMC_ENABLED_P(low)) {
printk(KERN_ERR "oprofile: P4 PMC not available\n");
return;
}
/* clear the cccrs we will use */
for (i = 0 ; i < num_counters ; i++) {
- if (unlikely(!CTRL_IS_RESERVED(msrs,i)))
+ if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
continue;
rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high);
CCCR_CLEAR(low);
@@ -576,14 +574,14 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs)
/* clear all escrs (including those outside our concern) */
for (i = num_counters; i < num_controls; i++) {
- if (unlikely(!CTRL_IS_RESERVED(msrs,i)))
+ if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
continue;
wrmsr(msrs->controls[i].addr, 0, 0);
}
/* setup all counters */
for (i = 0 ; i < num_counters ; ++i) {
- if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs,i))) {
+ if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs, i))) {
reset_value[i] = counter_config[i].count;
pmc_setup_one_p4_counter(i);
CTR_WRITE(counter_config[i].count, VIRT_CTR(stag, i));
@@ -603,11 +601,11 @@ static int p4_check_ctrs(struct pt_regs * const regs,
stag = get_stagger();
for (i = 0; i < num_counters; ++i) {
-
- if (!reset_value[i])
+
+ if (!reset_value[i])
continue;
- /*
+ /*
* there is some eccentricity in the hardware which
* requires that we perform 2 extra corrections:
*
@@ -616,24 +614,24 @@ static int p4_check_ctrs(struct pt_regs * const regs,
*
* - write the counter back twice to ensure it gets
* updated properly.
- *
+ *
* the former seems to be related to extra NMIs happening
* during the current NMI; the latter is reported as errata
* N15 in intel doc 249199-029, pentium 4 specification
* update, though their suggested work-around does not
* appear to solve the problem.
*/
-
+
real = VIRT_CTR(stag, i);
CCCR_READ(low, high, real);
- CTR_READ(ctr, high, real);
+ CTR_READ(ctr, high, real);
if (CCCR_OVF_P(low) || CTR_OVERFLOW_P(ctr)) {
oprofile_add_sample(regs, i);
- CTR_WRITE(reset_value[i], real);
+ CTR_WRITE(reset_value[i], real);
CCCR_CLEAR_OVF(low);
CCCR_WRITE(low, high, real);
- CTR_WRITE(reset_value[i], real);
+ CTR_WRITE(reset_value[i], real);
}
}
@@ -683,15 +681,16 @@ static void p4_shutdown(struct op_msrs const * const msrs)
int i;
for (i = 0 ; i < num_counters ; ++i) {
- if (CTR_IS_RESERVED(msrs,i))
+ if (CTR_IS_RESERVED(msrs, i))
release_perfctr_nmi(msrs->counters[i].addr);
}
- /* some of the control registers are specially reserved in
+ /*
+ * some of the control registers are specially reserved in
* conjunction with the counter registers (hence the starting offset).
* This saves a few bits.
*/
for (i = num_counters ; i < num_controls ; ++i) {
- if (CTRL_IS_RESERVED(msrs,i))
+ if (CTRL_IS_RESERVED(msrs, i))
release_evntsel_nmi(msrs->controls[i].addr);
}
}
diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h
index 45b605fa71d..05a0261ba0c 100644
--- a/arch/x86/oprofile/op_x86_model.h
+++ b/arch/x86/oprofile/op_x86_model.h
@@ -32,6 +32,8 @@ struct pt_regs;
* various x86 CPU models' perfctr support.
*/
struct op_x86_model_spec {
+ int (*init)(struct oprofile_operations *ops);
+ void (*exit)(void);
unsigned int const num_counters;
unsigned int const num_controls;
void (*fill_in_addresses)(struct op_msrs * const msrs);
@@ -46,6 +48,6 @@ struct op_x86_model_spec {
extern struct op_x86_model_spec const op_ppro_spec;
extern struct op_x86_model_spec const op_p4_spec;
extern struct op_x86_model_spec const op_p4_ht2_spec;
-extern struct op_x86_model_spec const op_athlon_spec;
+extern struct op_x86_model_spec const op_amd_spec;
#endif /* OP_X86_MODEL_H */
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index 9304c455507..ed982273fb8 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -5,6 +5,7 @@
* @remark Read the file COPYING
*
* @author John Levon <levon@movementarian.org>
+ * @author Barry Kasindorf
*
* This is the core of the buffer management. Each
* CPU buffer is processed and entered into the
@@ -33,7 +34,7 @@
#include "event_buffer.h"
#include "cpu_buffer.h"
#include "buffer_sync.h"
-
+
static LIST_HEAD(dying_tasks);
static LIST_HEAD(dead_tasks);
static cpumask_t marked_cpus = CPU_MASK_NONE;
@@ -48,10 +49,11 @@ static void process_task_mortuary(void);
* Can be invoked from softirq via RCU callback due to
* call_rcu() of the task struct, hence the _irqsave.
*/
-static int task_free_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+task_free_notify(struct notifier_block *self, unsigned long val, void *data)
{
unsigned long flags;
- struct task_struct * task = data;
+ struct task_struct *task = data;
spin_lock_irqsave(&task_mortuary, flags);
list_add(&task->tasks, &dying_tasks);
spin_unlock_irqrestore(&task_mortuary, flags);
@@ -62,13 +64,14 @@ static int task_free_notify(struct notifier_block * self, unsigned long val, voi
/* The task is on its way out. A sync of the buffer means we can catch
* any remaining samples for this task.
*/
-static int task_exit_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+task_exit_notify(struct notifier_block *self, unsigned long val, void *data)
{
/* To avoid latency problems, we only process the current CPU,
* hoping that most samples for the task are on this CPU
*/
sync_buffer(raw_smp_processor_id());
- return 0;
+ return 0;
}
@@ -77,11 +80,12 @@ static int task_exit_notify(struct notifier_block * self, unsigned long val, voi
* we don't lose any. This does not have to be exact, it's a QoI issue
* only.
*/
-static int munmap_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+munmap_notify(struct notifier_block *self, unsigned long val, void *data)
{
unsigned long addr = (unsigned long)data;
- struct mm_struct * mm = current->mm;
- struct vm_area_struct * mpnt;
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *mpnt;
down_read(&mm->mmap_sem);
@@ -99,11 +103,12 @@ static int munmap_notify(struct notifier_block * self, unsigned long val, void *
return 0;
}
-
+
/* We need to be told about new modules so we don't attribute to a previously
* loaded module, or drop the samples on the floor.
*/
-static int module_load_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+module_load_notify(struct notifier_block *self, unsigned long val, void *data)
{
#ifdef CONFIG_MODULES
if (val != MODULE_STATE_COMING)
@@ -118,7 +123,7 @@ static int module_load_notify(struct notifier_block * self, unsigned long val, v
return 0;
}
-
+
static struct notifier_block task_free_nb = {
.notifier_call = task_free_notify,
};
@@ -135,7 +140,7 @@ static struct notifier_block module_load_nb = {
.notifier_call = module_load_notify,
};
-
+
static void end_sync(void)
{
end_cpu_work();
@@ -208,14 +213,14 @@ static inline unsigned long fast_get_dcookie(struct path *path)
* not strictly necessary but allows oprofile to associate
* shared-library samples with particular applications
*/
-static unsigned long get_exec_dcookie(struct mm_struct * mm)
+static unsigned long get_exec_dcookie(struct mm_struct *mm)
{
unsigned long cookie = NO_COOKIE;
- struct vm_area_struct * vma;
-
+ struct vm_area_struct *vma;
+
if (!mm)
goto out;
-
+
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (!vma->vm_file)
continue;
@@ -235,13 +240,14 @@ out:
* sure to do this lookup before a mm->mmap modification happens so
* we don't lose track.
*/
-static unsigned long lookup_dcookie(struct mm_struct * mm, unsigned long addr, off_t * offset)
+static unsigned long
+lookup_dcookie(struct mm_struct *mm, unsigned long addr, off_t *offset)
{
unsigned long cookie = NO_COOKIE;
- struct vm_area_struct * vma;
+ struct vm_area_struct *vma;
for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
-
+
if (addr < vma->vm_start || addr >= vma->vm_end)
continue;
@@ -263,9 +269,20 @@ static unsigned long lookup_dcookie(struct mm_struct * mm, unsigned long addr, o
return cookie;
}
+static void increment_tail(struct oprofile_cpu_buffer *b)
+{
+ unsigned long new_tail = b->tail_pos + 1;
+
+ rmb(); /* be sure fifo pointers are synchromized */
+
+ if (new_tail < b->buffer_size)
+ b->tail_pos = new_tail;
+ else
+ b->tail_pos = 0;
+}
static unsigned long last_cookie = INVALID_COOKIE;
-
+
static void add_cpu_switch(int i)
{
add_event_entry(ESCAPE_CODE);
@@ -278,16 +295,16 @@ static void add_kernel_ctx_switch(unsigned int in_kernel)
{
add_event_entry(ESCAPE_CODE);
if (in_kernel)
- add_event_entry(KERNEL_ENTER_SWITCH_CODE);
+ add_event_entry(KERNEL_ENTER_SWITCH_CODE);
else
- add_event_entry(KERNEL_EXIT_SWITCH_CODE);
+ add_event_entry(KERNEL_EXIT_SWITCH_CODE);
}
-
+
static void
-add_user_ctx_switch(struct task_struct const * task, unsigned long cookie)
+add_user_ctx_switch(struct task_struct const *task, unsigned long cookie)
{
add_event_entry(ESCAPE_CODE);
- add_event_entry(CTX_SWITCH_CODE);
+ add_event_entry(CTX_SWITCH_CODE);
add_event_entry(task->pid);
add_event_entry(cookie);
/* Another code for daemon back-compat */
@@ -296,7 +313,7 @@ add_user_ctx_switch(struct task_struct const * task, unsigned long cookie)
add_event_entry(task->tgid);
}
-
+
static void add_cookie_switch(unsigned long cookie)
{
add_event_entry(ESCAPE_CODE);
@@ -304,13 +321,78 @@ static void add_cookie_switch(unsigned long cookie)
add_event_entry(cookie);
}
-
+
static void add_trace_begin(void)
{
add_event_entry(ESCAPE_CODE);
add_event_entry(TRACE_BEGIN_CODE);
}
+#ifdef CONFIG_OPROFILE_IBS
+
+#define IBS_FETCH_CODE_SIZE 2
+#define IBS_OP_CODE_SIZE 5
+#define IBS_EIP(offset) \
+ (((struct op_sample *)&cpu_buf->buffer[(offset)])->eip)
+#define IBS_EVENT(offset) \
+ (((struct op_sample *)&cpu_buf->buffer[(offset)])->event)
+
+/*
+ * Add IBS fetch and op entries to event buffer
+ */
+static void add_ibs_begin(struct oprofile_cpu_buffer *cpu_buf, int code,
+ int in_kernel, struct mm_struct *mm)
+{
+ unsigned long rip;
+ int i, count;
+ unsigned long ibs_cookie = 0;
+ off_t offset;
+
+ increment_tail(cpu_buf); /* move to RIP entry */
+
+ rip = IBS_EIP(cpu_buf->tail_pos);
+
+#ifdef __LP64__
+ rip += IBS_EVENT(cpu_buf->tail_pos) << 32;
+#endif
+
+ if (mm) {
+ ibs_cookie = lookup_dcookie(mm, rip, &offset);
+
+ if (ibs_cookie == NO_COOKIE)
+ offset = rip;
+ if (ibs_cookie == INVALID_COOKIE) {
+ atomic_inc(&oprofile_stats.sample_lost_no_mapping);
+ offset = rip;
+ }
+ if (ibs_cookie != last_cookie) {
+ add_cookie_switch(ibs_cookie);
+ last_cookie = ibs_cookie;
+ }
+ } else
+ offset = rip;
+
+ add_event_entry(ESCAPE_CODE);
+ add_event_entry(code);
+ add_event_entry(offset); /* Offset from Dcookie */
+
+ /* we send the Dcookie offset, but send the raw Linear Add also*/
+ add_event_entry(IBS_EIP(cpu_buf->tail_pos));
+ add_event_entry(IBS_EVENT(cpu_buf->tail_pos));
+
+ if (code == IBS_FETCH_CODE)
+ count = IBS_FETCH_CODE_SIZE; /*IBS FETCH is 2 int64s*/
+ else
+ count = IBS_OP_CODE_SIZE; /*IBS OP is 5 int64s*/
+
+ for (i = 0; i < count; i++) {
+ increment_tail(cpu_buf);
+ add_event_entry(IBS_EIP(cpu_buf->tail_pos));
+ add_event_entry(IBS_EVENT(cpu_buf->tail_pos));
+ }
+}
+
+#endif
static void add_sample_entry(unsigned long offset, unsigned long event)
{
@@ -319,13 +401,13 @@ static void add_sample_entry(unsigned long offset, unsigned long event)
}
-static int add_us_sample(struct mm_struct * mm, struct op_sample * s)
+static int add_us_sample(struct mm_struct *mm, struct op_sample *s)
{
unsigned long cookie;
off_t offset;
-
- cookie = lookup_dcookie(mm, s->eip, &offset);
-
+
+ cookie = lookup_dcookie(mm, s->eip, &offset);
+
if (cookie == INVALID_COOKIE) {
atomic_inc(&oprofile_stats.sample_lost_no_mapping);
return 0;
@@ -341,13 +423,13 @@ static int add_us_sample(struct mm_struct * mm, struct op_sample * s)
return 1;
}
-
+
/* Add a sample to the global event buffer. If possible the
* sample is converted into a persistent dentry/offset pair
* for later lookup from userspace.
*/
static int
-add_sample(struct mm_struct * mm, struct op_sample * s, int in_kernel)
+add_sample(struct mm_struct *mm, struct op_sample *s, int in_kernel)
{
if (in_kernel) {
add_sample_entry(s->eip, s->event);
@@ -359,9 +441,9 @@ add_sample(struct mm_struct * mm, struct op_sample * s, int in_kernel)
}
return 0;
}
-
-static void release_mm(struct mm_struct * mm)
+
+static void release_mm(struct mm_struct *mm)
{
if (!mm)
return;
@@ -370,9 +452,9 @@ static void release_mm(struct mm_struct * mm)
}
-static struct mm_struct * take_tasks_mm(struct task_struct * task)
+static struct mm_struct *take_tasks_mm(struct task_struct *task)
{
- struct mm_struct * mm = get_task_mm(task);
+ struct mm_struct *mm = get_task_mm(task);
if (mm)
down_read(&mm->mmap_sem);
return mm;
@@ -383,10 +465,10 @@ static inline int is_code(unsigned long val)
{
return val == ESCAPE_CODE;
}
-
+
/* "acquire" as many cpu buffer slots as we can */
-static unsigned long get_slots(struct oprofile_cpu_buffer * b)
+static unsigned long get_slots(struct oprofile_cpu_buffer *b)
{
unsigned long head = b->head_pos;
unsigned long tail = b->tail_pos;
@@ -412,19 +494,6 @@ static unsigned long get_slots(struct oprofile_cpu_buffer * b)
}
-static void increment_tail(struct oprofile_cpu_buffer * b)
-{
- unsigned long new_tail = b->tail_pos + 1;
-
- rmb();
-
- if (new_tail < b->buffer_size)
- b->tail_pos = new_tail;
- else
- b->tail_pos = 0;
-}
-
-
/* Move tasks along towards death. Any tasks on dead_tasks
* will definitely have no remaining references in any
* CPU buffers at this point, because we use two lists,
@@ -435,8 +504,8 @@ static void process_task_mortuary(void)
{
unsigned long flags;
LIST_HEAD(local_dead_tasks);
- struct task_struct * task;
- struct task_struct * ttask;
+ struct task_struct *task;
+ struct task_struct *ttask;
spin_lock_irqsave(&task_mortuary, flags);
@@ -493,7 +562,7 @@ void sync_buffer(int cpu)
{
struct oprofile_cpu_buffer *cpu_buf = &per_cpu(cpu_buffer, cpu);
struct mm_struct *mm = NULL;
- struct task_struct * new;
+ struct task_struct *new;
unsigned long cookie = 0;
int in_kernel = 1;
unsigned int i;
@@ -501,7 +570,7 @@ void sync_buffer(int cpu)
unsigned long available;
mutex_lock(&buffer_mutex);
-
+
add_cpu_switch(cpu);
/* Remember, only we can modify tail_pos */
@@ -509,8 +578,8 @@ void sync_buffer(int cpu)
available = get_slots(cpu_buf);
for (i = 0; i < available; ++i) {
- struct op_sample * s = &cpu_buf->buffer[cpu_buf->tail_pos];
-
+ struct op_sample *s = &cpu_buf->buffer[cpu_buf->tail_pos];
+
if (is_code(s->eip)) {
if (s->event <= CPU_IS_KERNEL) {
/* kernel/userspace switch */
@@ -521,8 +590,18 @@ void sync_buffer(int cpu)
} else if (s->event == CPU_TRACE_BEGIN) {
state = sb_bt_start;
add_trace_begin();
+#ifdef CONFIG_OPROFILE_IBS
+ } else if (s->event == IBS_FETCH_BEGIN) {
+ state = sb_bt_start;
+ add_ibs_begin(cpu_buf,
+ IBS_FETCH_CODE, in_kernel, mm);
+ } else if (s->event == IBS_OP_BEGIN) {
+ state = sb_bt_start;
+ add_ibs_begin(cpu_buf,
+ IBS_OP_CODE, in_kernel, mm);
+#endif
} else {
- struct mm_struct * oldmm = mm;
+ struct mm_struct *oldmm = mm;
/* userspace context switch */
new = (struct task_struct *)s->event;
@@ -533,13 +612,11 @@ void sync_buffer(int cpu)
cookie = get_exec_dcookie(mm);
add_user_ctx_switch(new, cookie);
}
- } else {
- if (state >= sb_bt_start &&
- !add_sample(mm, s, in_kernel)) {
- if (state == sb_bt_start) {
- state = sb_bt_ignore;
- atomic_inc(&oprofile_stats.bt_lost_no_mapping);
- }
+ } else if (state >= sb_bt_start &&
+ !add_sample(mm, s, in_kernel)) {
+ if (state == sb_bt_start) {
+ state = sb_bt_ignore;
+ atomic_inc(&oprofile_stats.bt_lost_no_mapping);
}
}
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 7ba78e6d210..e1bd5a937f6 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -5,6 +5,7 @@
* @remark Read the file COPYING
*
* @author John Levon <levon@movementarian.org>
+ * @author Barry Kasindorf <barry.kasindorf@amd.com>
*
* Each CPU has a local buffer that stores PC value/event
* pairs. We also log context switches when we notice them.
@@ -209,7 +210,7 @@ static int log_sample(struct oprofile_cpu_buffer * cpu_buf, unsigned long pc,
return 1;
}
-static int oprofile_begin_trace(struct oprofile_cpu_buffer * cpu_buf)
+static int oprofile_begin_trace(struct oprofile_cpu_buffer *cpu_buf)
{
if (nr_available_slots(cpu_buf) < 4) {
cpu_buf->sample_lost_overflow++;
@@ -254,6 +255,75 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
oprofile_add_ext_sample(pc, regs, event, is_kernel);
}
+#ifdef CONFIG_OPROFILE_IBS
+
+#define MAX_IBS_SAMPLE_SIZE 14
+static int log_ibs_sample(struct oprofile_cpu_buffer *cpu_buf,
+ unsigned long pc, int is_kernel, unsigned int *ibs, int ibs_code)
+{
+ struct task_struct *task;
+
+ cpu_buf->sample_received++;
+
+ if (nr_available_slots(cpu_buf) < MAX_IBS_SAMPLE_SIZE) {
+ cpu_buf->sample_lost_overflow++;
+ return 0;
+ }
+
+ is_kernel = !!is_kernel;
+
+ /* notice a switch from user->kernel or vice versa */
+ if (cpu_buf->last_is_kernel != is_kernel) {
+ cpu_buf->last_is_kernel = is_kernel;
+ add_code(cpu_buf, is_kernel);
+ }
+
+ /* notice a task switch */
+ if (!is_kernel) {
+ task = current;
+
+ if (cpu_buf->last_task != task) {
+ cpu_buf->last_task = task;
+ add_code(cpu_buf, (unsigned long)task);
+ }
+ }
+
+ add_code(cpu_buf, ibs_code);
+ add_sample(cpu_buf, ibs[0], ibs[1]);
+ add_sample(cpu_buf, ibs[2], ibs[3]);
+ add_sample(cpu_buf, ibs[4], ibs[5]);
+
+ if (ibs_code == IBS_OP_BEGIN) {
+ add_sample(cpu_buf, ibs[6], ibs[7]);
+ add_sample(cpu_buf, ibs[8], ibs[9]);
+ add_sample(cpu_buf, ibs[10], ibs[11]);
+ }
+
+ return 1;
+}
+
+void oprofile_add_ibs_sample(struct pt_regs *const regs,
+ unsigned int * const ibs_sample, u8 code)
+{
+ int is_kernel = !user_mode(regs);
+ unsigned long pc = profile_pc(regs);
+
+ struct oprofile_cpu_buffer *cpu_buf =
+ &per_cpu(cpu_buffer, smp_processor_id());
+
+ if (!backtrace_depth) {
+ log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code);
+ return;
+ }
+
+ /* if log_sample() fails we can't backtrace since we lost the source
+ * of this event */
+ if (log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code))
+ oprofile_ops.backtrace(regs, backtrace_depth);
+}
+
+#endif
+
void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
{
struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
@@ -296,7 +366,7 @@ static void wq_sync_buffer(struct work_struct *work)
struct oprofile_cpu_buffer * b =
container_of(work, struct oprofile_cpu_buffer, work.work);
if (b->cpu != smp_processor_id()) {
- printk("WQ on CPU%d, prefer CPU%d\n",
+ printk(KERN_DEBUG "WQ on CPU%d, prefer CPU%d\n",
smp_processor_id(), b->cpu);
}
sync_buffer(b->cpu);
diff --git a/drivers/oprofile/cpu_buffer.h b/drivers/oprofile/cpu_buffer.h
index c3e366b5226..9c44d004da6 100644
--- a/drivers/oprofile/cpu_buffer.h
+++ b/drivers/oprofile/cpu_buffer.h
@@ -55,5 +55,7 @@ void cpu_buffer_reset(struct oprofile_cpu_buffer * cpu_buf);
/* transient events for the CPU buffer -> event buffer */
#define CPU_IS_KERNEL 1
#define CPU_TRACE_BEGIN 2
+#define IBS_FETCH_BEGIN 3
+#define IBS_OP_BEGIN 4
#endif /* OPROFILE_CPU_BUFFER_H */
diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index 041bb31100f..bcb8f725427 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -36,6 +36,8 @@
#define XEN_ENTER_SWITCH_CODE 10
#define SPU_PROFILING_CODE 11
#define SPU_CTX_SWITCH_CODE 12
+#define IBS_FETCH_CODE 13
+#define IBS_OP_CODE 14
struct super_block;
struct dentry;
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index f1624b39675..f719d91afd9 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -497,6 +497,11 @@
#define PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP 0x1101
#define PCI_DEVICE_ID_AMD_K8_NB_MEMCTL 0x1102
#define PCI_DEVICE_ID_AMD_K8_NB_MISC 0x1103
+#define PCI_DEVICE_ID_AMD_10H_NB_HT 0x1200
+#define PCI_DEVICE_ID_AMD_10H_NB_MAP 0x1201
+#define PCI_DEVICE_ID_AMD_10H_NB_DRAM 0x1202
+#define PCI_DEVICE_ID_AMD_10H_NB_MISC 0x1203
+#define PCI_DEVICE_ID_AMD_10H_NB_LINK 0x1204
#define PCI_DEVICE_ID_AMD_LANCE 0x2000
#define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001
#define PCI_DEVICE_ID_AMD_SCSI 0x2020
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-11 12:12:08 +0000